EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[main]Upgrade cann to 8.3rc2 (#4350)

Browse Source 
### What this PR does / why we need it?
Upgrade cann to 8.3rc2

### Does this PR introduce _any_ user-facing change?
Yes, docker image will use 8.3.RC2


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
SILONG ZENG
2025-11-28 14:06:01 +08:00
committed by GitHub
parent 755b635844
commit ab37a7d5ae
23 changed files with 40 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/Dockerfile.buildwheel vendored
View File

@@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project. # This file is a part of the vllm-ascend project.
# #
ARG PY_VERSION=3.11 ARG PY_VERSION=3.11
FROM quay.io/ascend/manylinux:8.3.rc1-910b-manylinux_2_28-py${PY_VERSION} FROM quay.io/ascend/manylinux:8.3.rc2-910b-manylinux_2_28-py${PY_VERSION}
ARG COMPILE_CUSTOM_KERNELS=1 ARG COMPILE_CUSTOM_KERNELS=1
ARG SOC_VERSION ARG SOC_VERSION

4
.github/workflows/_e2e_nightly_multi_node.yaml vendored
View File

@@ -15,7 +15,7 @@ on:
required: false required: false
type: string type: string
description: base image for pods description: base image for pods
default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11" default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11"
config_file_path: config_file_path:
required: true required: true
type: string type: string
@@ -69,7 +69,7 @@ jobs:
# This is the runner with no NPU for k8s controller # This is the runner with no NPU for k8s controller
runs-on: ${{ inputs.runner }} runs-on: ${{ inputs.runner }}
container: container:
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11 image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
env: env:
KUBECONFIG: /tmp/kubeconfig KUBECONFIG: /tmp/kubeconfig
KUBECTL: /root/.cache/.kube/kubectl KUBECTL: /root/.cache/.kube/kubectl

2
.github/workflows/_e2e_nightly_single_node.yaml vendored
View File

@@ -29,7 +29,7 @@ on:
image: image:
required: false required: false
type: string type: string
default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11" default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11"
tests: tests:
required: true required: true
type: string type: string

7
.github/workflows/_e2e_nightly_single_node_models.yaml vendored
View File

@@ -59,7 +59,7 @@ jobs:
name: ${{inputs.model_list}} accuracy test name: ${{inputs.model_list}} accuracy test
runs-on: ${{ inputs.runner }} runs-on: ${{ inputs.runner }}
container: container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11 image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
env: env:
VLLM_USE_MODELSCOPE: True VLLM_USE_MODELSCOPE: True
GHA_VLLM_ASCEND_VERSION: ${{ inputs.vllm-ascend }} GHA_VLLM_ASCEND_VERSION: ${{ inputs.vllm-ascend }}
@@ -108,10 +108,7 @@ jobs:
if: ${{ inputs.runner == 'linux-aarch64-a2-4' && contains(inputs.model_list, 'Qwen3-Next-80B-A3B-Instruct') }} if: ${{ inputs.runner == 'linux-aarch64-a2-4' && contains(inputs.model_list, 'Qwen3-Next-80B-A3B-Instruct') }}
shell: bash -l {0} shell: bash -l {0}
run: | run: |
wget -q https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/Ascend-BiSheng-toolkit_aarch64.run -O /tmp/Ascend-BiSheng-toolkit_aarch64.run . /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
chmod a+x /tmp/Ascend-BiSheng-toolkit_aarch64.run
/tmp/Ascend-BiSheng-toolkit_aarch64.run --install
. /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20250914-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl" python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20250914-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
- name: Resolve vllm-ascend version - name: Resolve vllm-ascend version

9
.github/workflows/_e2e_test.yaml vendored
View File

@@ -211,7 +211,7 @@ jobs:
if: ${{ needs.e2e.result == 'success' && needs.e2e-2-cards.result == 'success' && inputs.type == 'full' }} if: ${{ needs.e2e.result == 'success' && needs.e2e-2-cards.result == 'success' && inputs.type == 'full' }}
runs-on: linux-aarch64-a3-4 runs-on: linux-aarch64-a3-4
container: container:
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11 image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
env: env:
VLLM_LOGGING_LEVEL: ERROR VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True VLLM_USE_MODELSCOPE: True
@@ -274,10 +274,7 @@ jobs:
- name: Install Ascend toolkit & triton_ascend (for Qwen3-Next-80B-A3B-Instruct) - name: Install Ascend toolkit & triton_ascend (for Qwen3-Next-80B-A3B-Instruct)
shell: bash -l {0} shell: bash -l {0}
run: | run: |
wget -q https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/Ascend-BiSheng-toolkit_aarch64.run -O /tmp/Ascend-BiSheng-toolkit_aarch64.run . /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
chmod a+x /tmp/Ascend-BiSheng-toolkit_aarch64.run
/tmp/Ascend-BiSheng-toolkit_aarch64.run --install
. /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20250914-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl" python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20250914-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
- name: Run vllm-project/vllm-ascend Qwen3 Next test - name: Run vllm-project/vllm-ascend Qwen3 Next test
@@ -287,5 +284,5 @@ jobs:
VLLM_WORKER_MULTIPROC_METHOD: spawn VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_USE_MODELSCOPE: True VLLM_USE_MODELSCOPE: True
run: | run: |
. /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh . /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
pytest -sv tests/e2e/multicard/test_qwen3_next.py pytest -sv tests/e2e/multicard/test_qwen3_next.py

2
.github/workflows/_nightly_image_build.yaml vendored
View File

@@ -45,7 +45,7 @@ jobs:
--network host \ --network host \
--platform linux/arm64 \ --platform linux/arm64 \
-f .github/Dockerfile.nightly.${TARGET} \ -f .github/Dockerfile.nightly.${TARGET} \
--build-arg CANN_VERSION="8.3.rc1" \ --build-arg CANN_VERSION="8.3.rc2" \
--build-arg UBUNTU_VERSION="22.04" \ --build-arg UBUNTU_VERSION="22.04" \
--build-arg PYTHON_VERSION="3.11" \ --build-arg PYTHON_VERSION="3.11" \
-t "$IMAGE_TAG" . -t "$IMAGE_TAG" .

2
.github/workflows/nightly_benchmarks.yaml vendored
View File

@@ -55,7 +55,7 @@ jobs:
vllm_ascend_branch: main vllm_ascend_branch: main
max-parallel: 1 max-parallel: 1
container: container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11 image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
volumes: volumes:
- /usr/local/dcmi:/usr/local/dcmi - /usr/local/dcmi:/usr/local/dcmi
- /usr/local/bin/npu-smi:/usr/local/bin/npu-smi - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi

2
.github/workflows/vllm_ascend_test_310p.yaml vendored
View File

@@ -58,7 +58,7 @@ jobs:
runs-on: ${{ matrix.os }} runs-on: ${{ matrix.os }}
container: container:
# TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready # TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-310p-ubuntu22.04-py3.11 image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-310p-ubuntu22.04-py3.11
env: env:
VLLM_LOGGING_LEVEL: ERROR VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True VLLM_USE_MODELSCOPE: True

2
.github/workflows/vllm_ascend_test_full_vllm_main.yaml vendored
View File

@@ -41,5 +41,5 @@ jobs:
with: with:
vllm: main vllm: main
runner: linux-aarch64-a2 runner: linux-aarch64-a2
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11 image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
type: full type: full

2
.github/workflows/vllm_ascend_test_pr_full.yaml vendored
View File

@@ -76,5 +76,5 @@ jobs:
with: with:
vllm: ${{ matrix.vllm_version }} vllm: ${{ matrix.vllm_version }}
runner: linux-aarch64-a2 runner: linux-aarch64-a2
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11 image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
type: full type: full

6
.github/workflows/vllm_ascend_test_pr_light.yaml vendored
View File

@@ -76,8 +76,8 @@ jobs:
if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }} if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }}
runs-on: ubuntu-latest runs-on: ubuntu-latest
container: container:
# fixme: vllm-ascend install failed with 8.3.rc1 on github action # fixme: vllm-ascend install failed with 8.3.rc2 on github action
image: quay.io/ascend/cann:8.2.rc1-910b-ubuntu22.04-py3.11 image: quay.io/ascend/cann:8.2.rc2-910b-ubuntu22.04-py3.11
env: env:
VLLM_LOGGING_LEVEL: ERROR VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True VLLM_USE_MODELSCOPE: True
@@ -151,5 +151,5 @@ jobs:
with: with:
vllm: ${{ matrix.vllm_version }} vllm: ${{ matrix.vllm_version }}
runner: linux-aarch64-a2 runner: linux-aarch64-a2
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11 image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
type: light type: light

2
.github/workflows/vllm_ascend_test_report.yaml vendored
View File

@@ -74,7 +74,7 @@ jobs:
with: with:
vllm: v0.11.2 vllm: v0.11.2
runner: ${{ matrix.runner }} runner: ${{ matrix.runner }}
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11 image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
model_list: ${{ toJson(matrix.model_list) }} model_list: ${{ toJson(matrix.model_list) }}
upload: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.vllm-ascend-version == 'latest' }} upload: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.vllm-ascend-version == 'latest' }}

2
Dockerfile
View File

@@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project. # This file is a part of the vllm-ascend project.
# #
FROM quay.io/ascend/cann:8.3.rc1-910b-ubuntu22.04-py3.11 FROM quay.io/ascend/cann:8.3.rc2-910b-ubuntu22.04-py3.11
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1 ARG COMPILE_CUSTOM_KERNELS=1

2
Dockerfile.310p
View File

@@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project. # This file is a part of the vllm-ascend project.
# #
FROM quay.io/ascend/cann:8.3.rc1-310p-ubuntu22.04-py3.11 FROM quay.io/ascend/cann:8.3.rc2-310p-ubuntu22.04-py3.11
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1 ARG COMPILE_CUSTOM_KERNELS=1

2
Dockerfile.310p.openEuler
View File

@@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project. # This file is a part of the vllm-ascend project.
# #
FROM quay.io/ascend/cann:8.3.rc1-310p-openeuler24.03-py3.11 FROM quay.io/ascend/cann:8.3.rc2-310p-openeuler24.03-py3.11
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1 ARG COMPILE_CUSTOM_KERNELS=1

2
Dockerfile.a3
View File

@@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project. # This file is a part of the vllm-ascend project.
# #
FROM quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11 FROM quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1 ARG COMPILE_CUSTOM_KERNELS=1

2
Dockerfile.a3.openEuler
View File

@@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project. # This file is a part of the vllm-ascend project.
# #
FROM quay.io/ascend/cann:8.3.rc1-a3-openeuler24.03-py3.11 FROM quay.io/ascend/cann:8.3.rc2-a3-openeuler24.03-py3.11
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1 ARG COMPILE_CUSTOM_KERNELS=1

2
Dockerfile.openEuler
View File

@@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project. # This file is a part of the vllm-ascend project.
# #
FROM quay.io/ascend/cann:8.3.rc1-910b-openeuler24.03-py3.11 FROM quay.io/ascend/cann:8.3.rc2-910b-openeuler24.03-py3.11
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1 ARG COMPILE_CUSTOM_KERNELS=1

2
docs/source/developer_guide/contribution/multi_node_test.md
View File

@@ -90,7 +90,7 @@ currently, the multi-node test workflow defined in the [vllm_ascend_test_nightly
uses: ./.github/workflows/_e2e_nightly_multi_node.yaml uses: ./.github/workflows/_e2e_nightly_multi_node.yaml
with: with:
soc_version: a3 soc_version: a3
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11 image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
replicas: 1 replicas: 1
size: ${{ matrix.test_config.size }} size: ${{ matrix.test_config.size }}
config_file_path: ${{ matrix.test_config.config_file_path }} config_file_path: ${{ matrix.test_config.config_file_path }}

20
docs/source/installation.md
View File

@@ -80,19 +80,19 @@ source vllm-ascend-env/bin/activate
pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple attrs 'numpy<2.0.0' decorator sympy cffi pyyaml pathlib2 psutil protobuf scipy requests absl-py wheel typing_extensions pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple attrs 'numpy<2.0.0' decorator sympy cffi pyyaml pathlib2 psutil protobuf scipy requests absl-py wheel typing_extensions
# Download and install the CANN package. # Download and install the CANN package.
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-toolkit_8.3.RC1_linux-"$(uname -i)".run wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-toolkit_8.3.RC1_linux-"$(uname -i)".run chmod +x ./Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run
./Ascend-cann-toolkit_8.3.RC1_linux-"$(uname -i)".run --full ./Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run --full
# https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C22B800TP052/Ascend-cann-kernels-910b_8.3.rc1_linux-aarch64.run # https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C22B800TP052/Ascend-cann-kernels-910b_8.3.rc2_linux-aarch64.run
source /usr/local/Ascend/ascend-toolkit/set_env.sh source /usr/local/Ascend/ascend-toolkit/set_env.sh
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run chmod +x ./Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run
./Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run --install ./Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run --install
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run chmod +x ./Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run
./Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run --install ./Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run --install
source /usr/local/Ascend/nnal/atb/set_env.sh source /usr/local/Ascend/nnal/atb/set_env.sh
``` ```

7
docs/source/tutorials/multi_npu_qwen3_next.md
View File

@@ -49,10 +49,7 @@ The [Triton Ascend](https://gitee.com/ascend/triton-ascend) is required when you
Install the Ascend BiSheng toolkit: Install the Ascend BiSheng toolkit:
```bash ```bash
wget https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/Ascend-BiSheng-toolkit_aarch64.run source /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
chmod a+x Ascend-BiSheng-toolkit_aarch64.run
./Ascend-BiSheng-toolkit_aarch64.run --install
source /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
``` ```
Install Triton Ascend: Install Triton Ascend:
@@ -76,7 +73,7 @@ Coming soon ...
Please make sure you have already executed the command: Please make sure you have already executed the command:
```bash ```bash
source /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh source /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
``` ```
:::::{tab-set} :::::{tab-set}

2
tests/e2e/singlecard/test_aclgraph.py
View File

@@ -137,7 +137,7 @@ def test_models_with_aclgraph_full_decode_only(
vllm_aclgraph_qwen_answers = [ vllm_aclgraph_qwen_answers = [
' \n\nTo solve this problem, we need to use the Law of Sines and Law of Cosines. Let me start by drawing triangle $ABC$ with the', ' \n\nTo solve this problem, we need to use the Law of Sines and Law of Cosines. Let me start by drawing triangle $ABC$ with the',
" \n\nTo solve this problem, we can use the fact that the expected value of the area of a triangle formed by two random points on a square's perimeter is", " \n\nTo solve this problem, we can use the fact that the expected value of the area of a triangle formed by two random points on a square's perimeter is",
'i$.\n\nLet $a, b, c$ be distinct numbers such that the equations $x^2 + ax + 1 = 0$ and' ' \n\nTo solve this problem, we can use the following approach: Let $ \\alpha $ be the common real root of the two equations. Then, we can'
] ]
vllm_aclgraph_ds_answers = [ vllm_aclgraph_ds_answers = [

2
tests/e2e/vllm_interface/vllm_test.cfg
View File

@@ -1,2 +1,2 @@
# Base docker image used to build the vllm-ascend e2e test image, which is built in the vLLM repository # Base docker image used to build the vllm-ascend e2e test image, which is built in the vLLM repository
BASE_IMAGE_NAME="quay.io/ascend/cann:8.3.rc1-910b-ubuntu22.04-py3.11" BASE_IMAGE_NAME="quay.io/ascend/cann:8.3.rc2-910b-ubuntu22.04-py3.11"